Skip to main content
Glama

send_manual_message

Send a manual operator message through the agent's outbound channel (Twilio, Meta, or webhook) when control mode is not engaged; record it as human-authored so agent style stays separate.

Instructions

Send a manual operator message through the same outbound channel as the agent (Twilio/Meta/webhook). Requires control_mode != engaged. Message is recorded as human-authored so the agent doesn't imitate the style if it resumes

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session_id": "<session_id>",
      "message": "<message>"
    },
    "name": "send_manual_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYesOperator message to send
session_idYesSession session_id string or UUID
idempotency_keyNoOptional idempotency key (1–200 characters). If omitted, it is derived from the message text within a 60-second window.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.2.4
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Chave de idempotência opcional (1–200 chars). Sem ela, a chave é derivada do texto da mensagem com janela de 60s."New value: +"Optional idempotency key (1–200 characters). If omitted, it is derived from the message text within a 60-second window."
    • changedInput schema / properties / message / description
      Previous value: -"Texto da mensagem manual a enviar"New value: +"Operator message to send"
    • changedInput schema / properties / session_id / description
      Previous value: -"session_id text (ou UUID id) da sessão"New value: +"Session session_id string or UUID"
  2. Changed1 schema field changedv2.2.2
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "Chave de idempotência opcional (1–200 chars). Sem ela, a chave é derivada do texto da mensagem com janela de 60s.",
      +  "maxLength": 200,
      +  "minLength": 1,
      +  "type": "string"
      +}
  3. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, it explains that the message is recorded as human-authored and why that matters — so the agent does not imitate the operator's style if it resumes — and that delivery uses the same external channel (consistent with openWorldHint). The precondition on control_mode is real behavioral context. It stops short of saying what error surfaces when the precondition fails or whether delivery is retried.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short clauses: what it sends, through which channel, under what precondition, plus the recording side effect. The precondition and the key semantic consequence are front-loaded with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a side-effecting send tool with no output schema, the definition covers the channel, the state precondition, and the authorship recording, which is what an agent needs to call it safely. Failure/error behavior and what a successful send returns are not covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters (message, session_id, idempotency_key) are already documented in the schema, including the 60-second derived-key behavior. The description adds no parameter-level detail beyond that structured data, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource, 'Send a manual operator message', and pins down the delivery mechanism: the same outbound channel as the agent, naming Twilio/Meta/webhook. The word 'manual' implicitly separates it from agent-generated conversation, but no sibling tool is named, so differentiation relies on inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It supplies a concrete gate for use: 'Requires `control_mode != engaged`', which tells the agent exactly when the call is valid. What is missing is the counterpart guidance — what to do when the agent is engaged (e.g., use an agent-turn tool instead) or whether the call fails or is rejected.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools